Sign up for our newsletter and get the latest big data news and analysis.

8 Ways 8 Billion Data Points Can Lower Diabetes Costs

Dealing with diabetes requires data. In the most basic sense, diabetes is managed by understanding information about blood sugar levels. To know what your blood sugar levels are, you use a blood glucose (BG) or continuous glucose monitor (CGM) for readings.

If your BG measures below (hypoglycemia) or above (hyperglycemia) a “safe” range, it can lead to fainting, seizures, heart attack, stroke, or liver and kidney problems. All of these complications are harrowing and costly. In fact, general treatment for diabetes is extraordinarily expensive — to the tune of over $850 billion per year globally!

Data is key in efforts to both lower those costs and enhance the quality of life for people with diabetes. Advances in healthcare information technology have made it possible to supply powerful data-based insights to care teams and individuals, refine measurement, and improve overall outcomes. The more data, the more accurate the representation of the condition and efficient the methodologies to treat it.

Insights derived from that data are powerful. In one chronic disease study, patients who adopted informed healthier habits saw a “40 percent reduction in average monthly emergency room visits and a 56 percent reduction in average hospital bills.” If a person can accurately and easily track their condition throughout the day, they are better equipped to self-manage disease and less likely to make unnecessary hospital visits.

With more than 100 million U.S. adults now living with diabetes or prediabetes, more and better data are essential. After years spent using technology to create tools that make it easy to capture BG and related relevant data, and collaborating with many partners to support people with diabetes and their care teams, we have amassed over eight-billion data points that reveal eight ways big data improves outcomes and lowers costs surrounding one of the most expensive chronic conditions plaguing the world.

  1. Self-care: Consistently collected data and rapid feedback can tell an individual what habits and behaviors are working towards keeping BG numbers in check — right down to the impact of eating certain types of food at certain times of day. Better self-understanding leads to better self-care. And that means fewer visits to the doctor, possibly less medication, and certainly less spend.
  2. Family support: Caring for a child, parent, or loved one with diabetes can be challenging. Data insights give caregivers visibility into the impact of meals, stress, exercise, and even play so they can better support cost-saving preventative health and improved well-being.
  3. Informed exertion: Activity and exercise data can be used to improve glycemic control. Understanding how specific activities directly tie to personal BG helps prevent dangerous hypoglycemic episodes and encourages safer, more effective workouts.
  4. Nutritional clarity: Healthier eating reduces the need for medication, insulin, and treatment. Tracking food choices to reveal what foods impact personal glucose levels provides clear means to understand everything from portion size to which foods to totally avoid.
  5. Remote support: It has been proven that providing remote support to people with diabetes in between regular doctor visits improves outcomes. Getting data-driven remote coaching and advice can help someone with diabetes stay on track and out of urgent care.
  6. Medication management: Diabetes medications are often taken at a different dose based on a person’s fasting glucose levels over a period of time. In the past, this involved manual and potentially error-prone calculations or just simply was never done. Data-driven insulin titration applications can now access an individual’s BG data directly from their glucose meter and automatically provide patients and their care teams with accurate readings. Further, such systems can recommend dose adjustments based on the care provider’s pre-configured treatment plan and/or published clinical guidelines.
  7. Hypoglycemia detection: Hypoglycemia is a common and often acute complication of diabetes. Devices providing frequent automatic readings, such as a CGM, can make monitoring easier and reduce the risk of costly hypoglycemic episodes and admissions.
  8. Algorithm improvement: Promising approaches in data science, health informatics, and machine learning are quickly evolving and opening new windows to more efficient diabetes management. Pattern recognition algorithms are now commonly used to spot anomalies, chart trends, and deliver treatment insight. With continued improvement in collection and access to good data (and lots of it!), this progression will continue to drive effective treatment and further lower diabetes-related costs.

Data science provides deep access to key aspects of chronic disease progression and treatment. Analyzing blood glucose levels and associated lifestyle data (diet, exercise, stress, etc.) can illuminate how to habituate better self-care, what medications should be prescribed and when, and what an effective personal care plan should look like. Insights created by the data collected is key to improving overall care and avoiding risk in diabetes management.

About the Author

David Conn is the Chief Commercial Officer at Glooko, a leading universal platform for diabetes management. Dave has spent the last 25 years as an executive at both large and start-up healthcare companies. For most of that time, Dave worked on developing, marketing and implementing innovations to help people with diabetes and clinical teams improve outcomes.

 

Sign up for the free insideBIGDATA newsletter.

Leave a Comment

*

Resource Links: